Looks like there is some quality reduction, but nonetheless 2s to generate a 5s video on a 5090 for WAN 2.1 is absolutely crazy. Excited to see more optimizations like this moving into 2026.

▲

avaer 4 minutes ago | parent | next [-]

Efficient realtime video diffusion will revolutionize the way people use computers even more so than LLMs.

I actually think we are already there with quality, but nobody is going to wait 10 minutes to do a task that takes 2 seconds.

If Sora/Kling/whatever ran cool locally 24/7 at 60FPS, would anyone ever build a UI? Or an OS?

I think it's worth watching the scaling graph.

▲

villgax 4 hours ago | parent | prev [-]

That’s not the actual time if you run it, encoding and decoding is extra

	▲	Lerc an hour ago \| parent [-]
		Nevertheless it does seem that generating will fairly soon become fast enough to extend a video clip in realtime. Autoregressive by the second. Integrated with a multi modal input model you would be very close to an AI avatar that would be extremely compelling.